Prove the lift · AI model performance evaluation

claude-sonnet-4-6 vs llama-3.1-8b

+15-point lift for claude-sonnet-4-6 on legal-research-qa

Test summary

This benchmark evaluates claude-sonnet-4-6 against llama-3.1-8b on the legal-research-qa v1 dataset (5 rows), scored by an LLM-as-judge (gpt-4o-mini). claude-sonnet-4-6 reached a 37% pass rate versus 22% for llama-3.1-8b — a +15-point lift.

Base model
llama-3.1-8b
via ollama · 22% pass rate
Refined model
claude-sonnet-4-6
via anthropic · 37% pass rate · 1.4s p95
Base pass rate
22%
Refined pass rate
37%
Refined p95
1.4s
Est. tokens saved
12.3K
+0pts
refined beats base on 5 rows
0%
Base model
0%
Invoked-refined
▲1 improved▼0 regressed●3 unchanged

Per-row results

1Summarize the holding of a cited appellate case0% → 0%0
2Determine whether a precedent was overruled0% → 0%0
3Identify the controlling statute in a fact pattern0% → 100%+100
4Extract the standard of review applied0% → 0%0
Prove the lift on your own data.

Run any two models over your tasks, judged automatically, and see the improvement — in seconds.

Try Invoked
Generated with Invoked · Browse all benchmarks